Prestidigitation logo

Prestidigitation

Community
Hmbown
prestidigitation

Prestidigitation transforms. It does not fix, build, scaffold, migrate, or actuate. If the user says "make this look better" or "convert this to that format" — use prestidigitation. If the user says "make this work" or "set this up" or "build this system" — use something else.

Overview

PublisherHmbown
RepositoryWizards-of-the-Ghosts
Skill nameprestidigitation
Stars
106
Forks
10
Bundled files
Instructions only
LicenseCC0-1.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Hmbown on GitHub. Read the source before you install it.

Installation

Install the Prestidigitation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts.git /tmp/Wizards-of-the-Ghosts
mkdir -p .claude/skills
cp -r /tmp/Wizards-of-the-Ghosts/generated/hermes/actions-access-and-automation/prestidigitation .claude/skills/prestidigitation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prestidigitation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Prestidigitation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Prestidigitation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Prestidigitation

Handle quick, low-stakes utility tasks that do not deserve a full spell.

What This Skill Does

Prestidigitation transforms. It does not fix, build, scaffold, migrate, or actuate. If the user says "make this look better" or "convert this to that format" — use prestidigitation. If the user says "make this work" or "set this up" or "build this system" — use something else. In this grimoire, Prestidigitation is treated as a hybrid spell with a shipping-now delivery profile. Canonical reference input: Prestidigitation (spell).

When To Use

  • Trigger this spell when the request contains:
  • Format/transform verbs: reformat, convert, sort, strip, encode, decode, tidy, clean, pretty-print
  • Scale qualifiers: quick, just, small, one-off, throwaway, simple, nothing fancy, straightforward
  • Artifact types: a table, a list, a single file, a string, a UUID, a snippet, a blob
  • Bounded counts: "about 20", "10 rows", "5 columns", "one line", "a few"
  • The task is cantrip-scale when all three are true:
  • The input fits in a single message or small file
  • The output is a single artifact (text, table, string, file)

Prerequisites

  • No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session.

Procedure

  1. Restate the target, the success condition, and any no-touch boundaries before taking action.
  2. Scope check: Confirm the task is single-input → single-output. If it spans multiple files or needs external services, stop and recommend the correct spell.
  3. Execute directly: Perform the transformation in-session. Do not create scaffolding, config files, or helper scripts. Do the work, do not build the tool to do the work.
  4. Return result: Output the artifact immediately. Add one sentence explaining what was done.
  5. Escalate if needed: If mid-execution the task reveals hidden complexity (nested edge cases, data too large, ambiguous requirements), stop and name the appropriate full spell.
  6. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

  • The completed small artifact, fix, or transformation.
  • A one-line note on what was done.
  • A flag if the task was actually bigger than it looked.

Pitfalls / Guardrails

  • Keep the theatrical framing, but name the concrete mechanism that makes the skill useful right now.
  • Do not use for: These look similar but belong to other spells:
  • Do not use for: | Looks like prestidigitation | Actually is | Why | |---|---|---| | "Fix the broken nginx config" | Debug/repair spell | Something is broken and needs diagnosis, not just reformatted | | "Set up Prettier + ESLint + pre-commit hooks" | Scaffolding spell | Multi-tool infrastructure setup, not a one-off transform | | "Convert our entire codebase from Python 2 to 3" | Migration spell | Hundreds of files, structural change, not a quick trick | | "Build a data visualization dashboard" | Build spell | Multi-component system with interactivity, not a single artifact | | "Create a fake dashboard that looks real" | Illusion/deception spell | Intent is to deceive, not to transform | | "Turn on the lights, set thermostat" | Device actuation spell | Physical world control, not text/data manipulation |
  • Do not use for: Rule of thumb: if the task requires reading multiple files, writing to multiple locations, installing dependencies, or touching infrastructure — it is not prestidigitation.

Verification

  • Check that the result includes every deliverable promised above.
  • Check that confirmed facts, assumptions, and inferences are visibly separated.
  • Check which parts are concrete actions versus framing, so the user can tell what is real now.

Example Invocation

text
/prestidigitation handle this quick task cleanly, without over-engineering it

Frequently asked questions

What does the Prestidigitation AI skill do?

Prestidigitation transforms. It does not fix, build, scaffold, migrate, or actuate. If the user says "make this look better" or "convert this to that format" — use prestidigitation. If the user says "make this work" or "set this up" or "build this system" — use something else.

Why use Prestidigitation on TypingMind?

Because you install it once and use it with any model. Prestidigitation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Prestidigitation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Hmbown/Wizards-of-the-Ghosts/tree/main/generated/hermes/actions-access-and-automation/prestidigitation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Prestidigitation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Prestidigitation?

As many as you like. As long as a model supports skills, you can use Prestidigitation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Prestidigitation AI skill free?

Yes. It is published on GitHub by Hmbown under the CC0-1.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇